Ziyi Lin

发表论文 16 篇 · 总被引 2459 次 · h-index 12

代表论文

• LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model (2023 · arXiv.org · 被引 764)
• Avatar-Net: Multi-scale Zero-Shot Style Transfer by Feature Decoration (2018 · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 被引 327)
• ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning for Action Recognition (2022 · Neural Information Processing Systems · 被引 319)
• SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models (2023 · arXiv.org · 被引 309)
• Frozen CLIP Models are Efficient Video Learners (2022 · European Conference on Computer Vision · 被引 301)
• SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models (2024 · International Conference on Machine Learning · 被引 160)